#
title: “Class 05: Data Visualization with GGPLOT” author: “Kira Jung (PID A16026398)” date: “April 24, 2023”
## Week 3 Data Visulization With ggplot2
# Install packages with install.package("ggplot2") and library(ggplot2).
# Q1: For which phases is data visualization important in our scientific workflows?
# A1: All of the above (communication of results, exploratory data analysis, detection of outliers).
# Q2: True or False? The ggplot2 package comes already installed with R?
#A2: FALSE.
# Q3: Which plot types are typically NOT used to compare distributions of numeric variables?
# A3: Network graphs
# Q4: Which statement about data visualization with ggplot2 is incorrect?
# A4: "ggplot2 is the only way to create plots in R".
library(ggplot2)
View(cars)
plot(cars)
ggplot(data=cars) + aes(x=speed, y=dist) + geom_point()
p <- ggplot(data=cars) + aes(x=speed, y=dist) + geom_point()
# Add a line geom with geom_line()
p + geom_line()
# Add a trendline close to the data
p + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
p + geom_smooth(method="lm")
## `geom_smooth()` using formula = 'y ~ x'
# Read in our drug expression data
url <- "https://bioboot.github.io/bimm143_S20/class-material/up_down_expression.txt"
genes <- read.delim(url)
head(genes)
## Gene Condition1 Condition2 State
## 1 A4GNT -3.6808610 -3.4401355 unchanging
## 2 AAAS 4.5479580 4.3864126 unchanging
## 3 AASDH 3.7190695 3.4787276 unchanging
## 4 AATF 5.0784720 5.0151916 unchanging
## 5 AATK 0.4711421 0.5598642 unchanging
## 6 AB015752.4 -3.6808610 -3.5921390 unchanging
View(genes)
# Q. how many genes in dataset = 5196
nrow(genes)
## [1] 5196
# Q. column names and number = (4) Gene, Condition1, Condition2, State
colnames(genes)
## [1] "Gene" "Condition1" "Condition2" "State"
ncol(genes)
## [1] 4
# Q. how many 'up' regulated genes = 127 genes
table(genes$State)
##
## down unchanging up
## 72 4997 127
# Q. What fraction of total genes are up-regulated = 2.4%
round((table(genes$State) / nrow(genes)) * 100, 2)
##
## down unchanging up
## 1.39 96.17 2.44
# Let's make a first plot attempt
g <- ggplot(data=genes) + aes(x=Condition1, y=Condition2, col=State) + geom_point()
# Add some color
g + scale_color_manual(values=c("blue", "gray", "red")) + labs(title="Gene expression changes", x="Control(no drug)", y="Condition 2") + theme_bw()
# 7 - Optional Portion
# installing the gapminder package
# install.packages("gapminder")
url <- "https://raw.githubusercontent.com/jennybc/gapminder/master/inst/extdata/gapminder.tsv"
gapminder <- read.delim(url)
# installing dplyr package
# install.packages("dplyr")
library(dplyr)
##
## Attaching package: 'dplyr'
##
## The following objects are masked from 'package:stats':
##
## filter, lag
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
gapminder_2007 <- gapminder %>% filter(year==2007)
# basic scatter plot of gapminder_2007 dataset
ggplot(gapminder_2007) + aes(x=gdpPercap, y=lifeExp) + geom_point(alpha=0.5)
# scatterplot of gapminder_2007 dataset with color and 4 variables
ggplot(gapminder_2007) + aes(x=gdpPercap, y=lifeExp, color=continent, size=pop) + geom_point(alpha=0.5)
# scatterplot of gapminder_2007 dataset, colored by numeric variable population
ggplot(gapminder_2007) + aes(x=gdpPercap, y=lifeExp, color=pop) + geom_point(alpha=0.8)
# Adjusting scale size of gapminder_2007 scatter plot to reflect population differences
ggplot(gapminder_2007) + aes(x=gdpPercap, y=lifeExp, size=pop) + geom_point(alpha=0.5) + scale_size_area(max_size=10)
# Q. Final 1957 and 2007 gapminder plots side by side.
library(dplyr)
gapminder_1957 <- gapminder %>% filter(year==1957 | year==2007)
ggplot(gapminder_1957) + geom_point(aes(x=gdpPercap, y=lifeExp, color=continent, size=pop), alpha=0.7) + scale_size_area(max_size=10) + facet_wrap(~year)
# 8 - Optional Bar Charts Section
gapminder_top5 <- gapminder %>% filter(year==2007) %>% arrange(desc(pop)) %>% top_n(5, pop)
# ggplot(gapminder_top5)
geom_col(aes(x=country, y=pop))
## mapping: x = ~country, y = ~pop
## geom_col: just = 0.5, width = NULL, na.rm = FALSE
## stat_identity: na.rm = FALSE
## position_stack
# Q. Bar chart showing life expectancy of 5 biggest countries by population in 2007.
ggplot(gapminder_top5) + geom_col(aes(x=country, y=lifeExp))
# Gapminder_top5 Bar Chart with color by population
ggplot(gapminder_top5) + geom_col(aes(x=country, y=pop, fill=continent))
# # Gapminder_top5 Bar Chart with color by life expectancy
ggplot(gapminder_top5) + geom_col(aes(x=country, y=pop, fill=lifeExp))
# Q.Gapminder_top5 Bar Chart by population
gapminder_top5 <- gapminder %>% filter(year==2007) %>% arrange(desc(pop)) %>% top_n(5, pop)
ggplot(gapminder_top5) + geom_col(aes(x=reorder(country, -pop), y=pop, fill=country, col="gray30", fill="none"))
## Warning: Duplicated aesthetics after name standardisation: fill
## Duplicated aesthetics after name standardisation: fill
# Flipping Bar Charts
head(USArrests)
## Murder Assault UrbanPop Rape
## Alabama 13.2 236 58 21.2
## Alaska 10.0 263 48 44.5
## Arizona 8.1 294 80 31.0
## Arkansas 8.8 190 50 19.5
## California 9.0 276 91 40.6
## Colorado 7.9 204 78 38.7
# USArrests$State <- rownames(USArrests)
# ggplot(USArrests) + aes(x=reorder(State, Murder), y=Murder) + geom_col() + coord_flip()
# ggplot(USArrests) + aes(x=reorder(State, Murder), y=Murder) + geom_point() + geom_segment(aes(x=State, xend=State, y=0, yend=Murder), color="blue") + coord_flip()
# 9 - Animation
# install.packages("gifski")
# install.packages("gganimate")
library(gapminder)
##
## Attaching package: 'gapminder'
##
## The following object is masked _by_ '.GlobalEnv':
##
## gapminder
library(gganimate)
ggplot(gapminder, aes(gdpPercap, lifeExp, size = pop, colour = country)) +
geom_point(alpha = 0.7, show.legend = FALSE) +
scale_colour_manual(values = country_colors) +
scale_size(range = c(2, 12)) +
scale_x_log10() + facet_wrap(~continent) + labs(title = 'Year: {frame_time}', x = 'GDP per capita', y = 'life expectancy') +
transition_time(year) +
shadow_wake(wake_length = 0.1, alpha = FALSE)
# 10 - Combining Plots
# install.packages("patchwork")
# library(patchwork)
p1 <- ggplot(mtcars) + geom_point(aes(mpg, disp))
p2 <- ggplot(mtcars) + geom_boxplot(aes(gear, disp, group = gear))
p3 <- ggplot(mtcars) + geom_smooth(aes(disp, qsec))
p4 <- ggplot(mtcars) + geom_bar(aes(carb))
# (p1 | p2 | p3) / p4
# Session Info
sessionInfo()
## R version 4.2.3 (2023-03-15 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 22621)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=English_United States.utf8
## [2] LC_CTYPE=English_United States.utf8
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.utf8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] gganimate_1.0.8 gapminder_1.0.0 dplyr_1.1.2 ggplot2_3.4.2
##
## loaded via a namespace (and not attached):
## [1] bslib_0.4.2 compiler_4.2.3 pillar_1.9.0 jquerylib_0.1.4
## [5] prettyunits_1.1.1 progress_1.2.2 tools_4.2.3 digest_0.6.31
## [9] lattice_0.21-8 nlme_3.1-162 jsonlite_1.8.4 evaluate_0.20
## [13] lifecycle_1.0.3 tibble_3.2.1 gtable_0.3.3 mgcv_1.8-42
## [17] pkgconfig_2.0.3 rlang_1.1.0 Matrix_1.5-4 cli_3.6.1
## [21] rstudioapi_0.14 yaml_2.3.7 xfun_0.39 fastmap_1.1.1
## [25] withr_2.5.0 knitr_1.42 hms_1.1.3 generics_0.1.3
## [29] vctrs_0.6.2 sass_0.4.5 grid_4.2.3 tidyselect_1.2.0
## [33] glue_1.6.2 R6_2.5.1 gifski_1.6.6-1 fansi_1.0.4
## [37] rmarkdown_2.21 tweenr_2.0.2 farver_2.1.1 magrittr_2.0.3
## [41] splines_4.2.3 scales_1.2.1 htmltools_0.5.5 colorspace_2.1-0
## [45] labeling_0.4.2 utf8_1.2.3 stringi_1.7.12 munsell_0.5.0
## [49] cachem_1.0.7 crayon_1.5.2